Borrowing it
Nothing to install: this file belongs to zotoio/CRUX-Compress. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zotoio/CRUX-Compress/main/.cursor/skills/crux-skill-memory-meditation-review/SKILL.mdgit clone --depth 1 https://github.com/zotoio/CRUX-CompressWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-meditation-review)<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-meditation-review"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-meditation-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zotoio/crux-compress/crux-skill-memory-meditation-review"><img src="https://agentmods.dev/badge/skills/zotoio/crux-compress/crux-skill-memory-meditation-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 96 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- low Excessive Agency · line 49 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.05191 |
| Opus 5 | $0.00000 | $0.02596 |
| Sonnet 5 | $0.00000 | $0.01038 |
| Haiku 4.5 | $0.00000 | $0.00519 |
Grade A, and why
crux-skill-memory-meditation-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRUX Skill: Memory Meditation — Adversarial Review
Implements the mandatory Adversarial Review function: quality gate over all editable meditation outputs across 13 dimensions, severity classification, ≤3-iteration loop with ESCALATE semantics, Pattern-B escalation with mandatory context field, and the Report-Skill Respawn Protocol (K9 + K10b) for Dim 13 findings.
When to Use
Load this skill when:
- The
crux-cursor-meditation-guideagent is spawned in Adversarial Review function (a sub-mode of Meditate) at step 10 of the depth-0 manager workflow - You are a fresh reviewer agent (new, clean context — no inherited assumptions from the depth-0 manager or any branch agent)
reviewerIteration ∈ {1, 2, 3}is set in the spawn prompt
Never load this skill in Research mode, Quick mode, Ensemble Aggregation mode, or Report generation — those are owned by their respective skill files.
Input Parameters (Adversarial Review invocation)
meditateMode: "research" | "quick" # mode of the meditation under review
reviewerIteration: 1 | 2 | 3 # 1-indexed, capped at 3
workingDir: "<absolute path to the meditation working directory>"
theming: { ... } # so the reviewer can flag homogenisation drift — REQUIRED
comprehensiveness: { ... } # so the reviewer can check level-conditional minima — REQUIRED
modelStrategy: { ... } # propagated unchanged by every spawn — REQUIRED (consistent with the propagation rule in the meditation-guide agent). The reviewer does not itself spawn model-specific children, but the payload is recorded in the review document for audit (e.g. "reviewer ran on caller's model because modelStrategy.mode == per_branch")
priorReviewPath: null | "<path>" # path to previous iteration's review document
Editable, Read-Only, and Never-Touched File Lists
The reviewer reads — but is the only agent permitted to rewrite during the cycle — the following files:
- Editable (can rewrite):
facets.md,consolidation.md, everybranch-*-depth-*-sub-*-*.md, everybranch-*-peer-review-*.md - Read-only (no rewrite):
facet-registry.yml,citations-index.yml(Research mode only),init-suggestions-{ts}.yml,finalisation-enhancements.yml - Never touched by the reviewer:
report-*.html,report-*.pdf,.facet-registry.lock/,facets-pending-*.yml,pending-facets-*.yml,confirmed-facets-*.yml
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 278 lines · 0 tokens per session scan A c257f69601fa
crux-skill-memory-meditation-review is a skill published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,191 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
notion-recipes
Use this skill when a user wants to turn meeting notes into a tracked Action Items database in Notion, or to bulk-edit, find-replace, normalize, or repair Notion database rows or page text at a scale past Notion's native find-and-replace limits. Uses easy-notion's MCP tools.
init-workspace-rules
Create agent rules.
template-pools-rules-tools
Fonds, rules, and tools integration exemplar — read resource pools, apply governance rules, validate tool manifests, and run combined integration.
Gauge Testing
Test automation with Gauge framework using Markdown specifications, step implementations in Java/Python/JavaScript/Ruby/C#, concepts, data-driven testing, and living documentation.
authoring-skills-and-rules
Author Skills (SKILL.md) and rules/instructions across Claude Code, Cursor, OpenCode, Codex, and GitHub Copilot. Covers frontmatter, file layout, activation, mirroring, and craft: progressive disclosure, Apply-when descriptions, leading words, playbook steps copied into todos, skip reasons, and the deletion test.…
web-scraping
Extract clean content from URLs via MCP. Use when the user asks to scrape a URL, read docs/blog/article pages, summarize a link, extract links, search page text, batch-scrape URLs, or get OG/title metadata without Firecrawl.